CN108268898A - A kind of electronic invoice user clustering method based on K-Means - Google Patents
A kind of electronic invoice user clustering method based on K-Means Download PDFInfo
- Publication number
- CN108268898A CN108268898A CN201810057864.5A CN201810057864A CN108268898A CN 108268898 A CN108268898 A CN 108268898A CN 201810057864 A CN201810057864 A CN 201810057864A CN 108268898 A CN108268898 A CN 108268898A
- Authority
- CN
- China
- Prior art keywords
- electronic invoice
- vector
- behavior data
- data
- consumer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of electronic invoice user clustering method based on K Means, including：It establishes electronic invoice consumer consumption behavior data clusters model and realizes electronic invoice consumer consumption behavior data matching method.Clustering Model method for building up includes：The consumer behavior data for choosing M electronic invoice user are sample data, establish the index series of electronic invoice consumer consumption behavior data clusters model, the indicator vector of sample data is calculated using big data technology, utilize the central point of K Means algorithms parameter vectors, obtain the feature vector of sample data namely the feature vector of Clustering Model.Electronic invoice consumer consumption behavior data matching method includes：Feature vector in the indicator vector and Clustering Model of example to be sorted is compared, obtain with the immediate feature vector V of example to be sorted, then example to be sorted belong to the corresponding electronic invoice users of V consumer behavior data classification.
Description
Technical field
The present invention relates to a kind of electronic invoice user clustering methods based on K-Means.
Background technology
In order to improve marketing operational effect, promoting team needs to find accurately electronic invoice user crowd, according to difference
The different characteristics of user crowd targetedly matches corresponding marketing program.Electronic invoice ticket information includes the consumption of user
Behavioral data is modeled by mathematical algorithm, is extracted consumer consumption behavior feature, is divided group so as to carry out user clustering, for difference
The user of feature carries out differentiation precision marketing operation and is of great significance.In sorting algorithm, K-Means algorithms are a kind of bases
In the Classic Clustering Algorithms of division methods, have and illegal vehicle in use identification is carried out based on this algorithm, achieve higher discrimination.
At present, the data dimension that group is divided to consider in traditional business for electronic invoice user is single, and user distinguishes effect
Difference, it is difficult to support the demand of precision marketing operation.
Invention content
In order to solve the above technical problem, the present invention provides a kind of electronic invoice user clustering sides based on K-Means
Method when carrying out precision marketing operation for electronic invoice user mainly for solution, can not divide group to screen asking for particular group
Topic.
A kind of electronic invoice user clustering method based on K-Means, including：Based on the electronic invoice customer consumption row
To establish the electronic invoice consumer consumption behavior data clusters model；Gather using the electronic invoice consumer consumption behavior data
Class model realizes the electronic invoice consumer consumption behavior Data Matching, and the electronic invoice consumer consumption behavior is gathered
Class.
Further, electronic invoice consumer consumption behavior data clusters model is established, including：Choose M (M ＞ 1) electronics
The consumer behavior data of invoice user are sample data；Establish the index sequence of electronic invoice consumer consumption behavior data clusters model
It arranges, the index number in index series is N (N >=1)；Index in index series calculates sample using big data technology
The indicator vector of data, the consumer behavior data of each electronic invoice user obtain an indicator vector；Utilize K-Means algorithms
The central point of parameter vector, obtains the feature vector of sample data, and the feature vector of each corresponds to a kind of electronic invoice
The consumer behavior data classification of user；The feature vector of sample data forms electronic invoice consumer consumption behavior data clusters mould
Type.
Further, electronic invoice consumer consumption behavior data matching method is realized, including：Choose any one electronics hair
The consumer behavior data of ticket user are as example to be sorted；According to the index of electronic invoice consumer consumption behavior data clusters model
Sequence calculates the indicator vector of example to be sorted；Feature vector in the indicator vector and Clustering Model of example to be sorted carries out
Comparison, obtain with the immediate feature vector V of example to be sorted, then example to be sorted belong to the corresponding electronic invoice users' of V
Consumer behavior data are classified.
Further, the choosing method of sample data includes：Made using all electronic invoice consumer consumption behavior data
For sample data, it is random or according to certain regular selected part electronic invoice consumer consumption behavior data as sample number
According to.
Further, the index in index series includes primary attribute, consumption attribute and liveness attribute；Primary attribute packet
Include gender, age and city rank；It consumes attribute and includes purchasing power, classification preference and Brang Preference；Liveness attribute includes the moon
Liveness, year liveness and active period.
Further, the method that the indicator vector of sample data is calculated using big data technology is included：To sample data into
Row cleaning and stipulations form preprocessed data vector, and carrying out z-score to preprocessed data vector standardizes to obtain sample data
Indicator vector.
Further, included using the method for the central point of K-Means algorithms parameter vector：
S1：K indicator vector is randomly selected from M indicator vector as initial center point, wherein M ＞ K, and K ＞ 1；
S2：To remaining (M-K) a indicator vector, each indicator vector is calculated to the distance of K initial center point, is referred to
The distance of mark vector to which initial center point is minimum, then indicator vector is divided to the corresponding classification of initial center point；
S3：Indicator vector is divided into K classification, calculates the central point each classified；
S4：Iteration carries out the calculating in S2 and S3, until the central point of K classification and the last K classification calculated
The equal or distance of central point is less than defined threshold value, then terminates interative computation；
The central point of K classification namely the central point of indicator vector that final operation obtains, what central point was classified for K
Feature vector.
Further, the feature vector of K classification is N-dimensional vector, and K N-dimensional vector forms electronic invoice customer consumption
Behavioral data Clustering Model.
Further, the method packet that the feature vector in the indicator vector and Clustering Model of example to be sorted is compared
It includes：The distance of all feature vectors in the indicator vector and Clustering Model of example to be sorted is calculated, wherein being apart from reckling
With the immediate feature vector V of example to be sorted.
The invention has the advantages that the consumer behavior data by extracting user from user's electronic invoice ticket information,
Introduce electronic invoice user gender, age, city rank, purchasing power, preference classification, active period, moon liveness, year liveness
Deng the composite factor for influencing consumer consumption behavior, structure influences the overall target sequence of consumer consumption behavior, in order to eliminate each finger
The difference of dimension, is standardized index between mark, using the index value after each criterion as N-dimensional vector, utilizes K-
MEANS clustering algorithms iterate to calculate out the central point of user Suo Fen groups, so as to fulfill to classifying and dividing users group, to carry out
Precision marketing operation provides support.
Description of the drawings
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution of the prior art
Embodiment or attached drawing needed to be used in the description of the prior art are briefly described, it should be apparent that, in being described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is the techniqueflow chart that the present invention is implemented；
Fig. 2 is the electronic invoice consumer consumption behavior data target sequence of the present invention；
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, described embodiment be part of the embodiment of the present invention rather than whole
Embodiment.
Fig. 1 is the techniqueflow chart implemented according to the present invention, as shown in Figure 1, this method comprises the following steps：
Step S101, the consumer behavior data for choosing M electronic invoice user are sample data；
As the selection of sample data, currently existing all electronic invoice consumer consumption behavior data can be selected to make
For sample data, subsequently calculated.In an alternate embodiment of the invention, it can be sent out in the way of random sampling from all electronics
Ticket consumer consumption behavior data selecting section divided data is as sample data.It, can also be according in another optional embodiment
Certain rule chooses sample data, such as rejects that information is imperfect, data of information fuzzy are as sample data.
Step S102 establishes the index series of electronic invoice consumer consumption behavior data clusters model；
Index in index series includes primary attribute, consumption attribute and liveness attribute；Primary attribute includes gender, year
Age and city rank；It consumes attribute and includes purchasing power, classification preference and Brang Preference；Liveness attribute includes moon liveness, year
Liveness and active period.Therefore in the present embodiment, index number is 9 in index series, i.e. N=9.
The calculating of each index is from electronic invoice user's registration information, electronic invoice ticket face data, user's statistical data.
Such as electronic invoice ticket face data includes：Tax-controlling machine number, purchaser's information, cargo or service name, are received seller information
The information such as money people, drawer, invoice codes, invoice number, date of making out an invoice, Amount in Total, the tax rate.
Step S103 calculates the indicator vector of the sample data using big data technology；
Using the preconditioning technique of big data, sample data is cleaned and stipulations form preprocessed data vector.
In practice, the data complexity of nominal value is various, such as all spending amounts and deduction amount of money situation can be listed in nominal value by part businessman
On, Amount in Total subtracts the numerical value after the deduction amount of money for spending amount, and real consumption product include multiple types, at this moment
It needs single invoice splitting into multiple ticket face datas and goes to handle, data after treatment form the data target of pretreatment
Vector carries out z-score to the indicator vector of pretreatment and standardizes to obtain the indicator vector P of sample datai, wherein (i=
1......M)。
Step S104 utilizes the central point of K-Means algorithms parameter vector；
1) K indicator vector is randomly selected from M indicator vector as initial center point, the usual M in engineering practice
K can be much larger than, the size of K depends on the categorical measure of data clusters, and K is smaller, and the classification divided is fewer, and the K the big, divides
Classification is bigger.
2) to remaining (M-K) a indicator vector, each indicator vector is calculated to the distance of K initial center point, is referred to
The distance of mark vector to which initial center point is minimum, then indicator vector is divided to the corresponding classification of initial center point；
3) indicator vector is divided into K classification, calculates the central point each classified；
2) and 3) 4) calculating during iteration carries out, until during the central point of K classification is classified with last K calculated
The equal or distance of heart point is less than defined threshold value, then terminates interative computation；
The central point of K classification namely the feature vector Q of sample data finally obtainedi, wherein (i=1.....K),
The feature vector of each corresponds to the consumer behavior data classification of electronic invoice user a kind of, and the feature vector of sample data is formed
Electronic invoice consumer consumption behavior data clusters model.
Step S105, the feature vector comparison in the indicator vector and Clustering Model of example to be sorted, obtains calculation to be sorted
Classification belonging to example；
For the Clustering Model formed, judge which classification the consumer behavior of a certain electronic invoice user belongs to,
Computational methods are：By the consumer behavior data of the user, that is, example to be sorted, gathered according to electronic invoice consumer consumption behavior data
The index series of class model calculates the indicator vector R of example to be sorted, calculates R to the feature vector Q of sample dataiDistance.
The classification that wherein the feature vector V minimum with R distances is represented, the classification belonging to example as to be sorted.
Claims (9)
- A kind of 1. electronic invoice user clustering method based on K-Means, which is characterized in that including：Electronic invoice consumer consumption behavior data clusters model is established based on electronic invoice consumer consumption behavior；Using electronic invoice consumer consumption behavior data described in the electronic invoice consumer consumption behavior data clusters model realization Matching, clusters the electronic invoice consumer consumption behavior.
- 2. according to the method described in claim 1, it is characterized in that, establish the electronic invoice consumer consumption behavior data clusters Model, including：The consumer behavior data for choosing M electronic invoice users are sample data, wherein M ＞ 1；Establish the index series of the electronic invoice consumer consumption behavior data clusters model, the index in the index series It counts as N, N >=1；According to the index in the index series, the indicator vector of the sample data, Mei Gesuo are calculated using big data technology The consumer behavior data for stating electronic invoice user obtain an indicator vector；The central point of the indicator vector is calculated using K-Means algorithms, obtains the feature vector of the sample data, each The feature vector corresponds to the consumer behavior data classification of electronic invoice user a kind of；The feature vector of the sample data forms the electronic invoice consumer consumption behavior data clusters model.
- 3. according to the method described in claim 1, it is characterized in that, realize the electronic invoice consumer consumption behavior Data Matching Method, including：The consumer behavior data of any one of electronic invoice user are chosen as example to be sorted；According to the index series of the electronic invoice consumer consumption behavior data clusters model, the finger of the example to be sorted is calculated Mark vector；The indicator vector of the example to be sorted is compared with the feature vector in the Clustering Model, obtains treating point with described The immediate described eigenvector V of class example, then the example to be sorted belong to the consumption of the corresponding electronic invoice users of V Behavioral data is classified.
- 4. according to the method described in claim 2, it is characterized in that, the choosing method of the sample data includes：Using all electronic invoice consumer consumption behavior data as the sample data, at random or according to certain Electronic invoice consumer consumption behavior data are as sample data described in regular selected part.
- 5. according to the method described in claim 2, it is characterized in that, the index in the index series includes primary attribute, disappears Take attribute and liveness attribute；The primary attribute includes gender, age and city rank；The consumption attribute includes purchase Power, classification preference and Brang Preference；The liveness attribute includes moon liveness, year liveness and active period.
- 6. according to the method described in claim 2, it is characterized in that, described calculate the sample data using big data technology The method of indicator vector includes：The sample data is cleaned and stipulations form preprocessed data vector, to the pre- place Reason data vector carries out z-score and standardizes to obtain the indicator vector of the sample data.
- 7. according to the method described in claim 2, it is characterized in that, described calculate the indicator vector using K-Means algorithms The method of central point include：S1：The K indicator vectors are randomly selected from the M indicator vectors as initial center point, wherein M ＞ K, and K ＞ 1；S2：To remaining (M-K) a indicator vector, each described indicator vector is calculated to the K initial center points Distance, the distance of the indicator vector to initial center point which described is minimum, then the indicator vector is divided to institute State the corresponding classification of initial center point；S3：The indicator vector is divided into K classification, calculates the central point of each classification；S4：Iteration carries out the calculating in S2 and S3, until the K points that the central point of described K classification is calculated with the last time The equal or distance of the central point of class is less than defined threshold value, then terminates interative computation；The central point of the K classification namely the central point of the indicator vector that final operation obtains, the central point is K The described eigenvector of a classification.
- 8. the method according to the description of claim 7 is characterized in that the described eigenvector of K classification is N-dimensional vector, K is a The N-dimensional vector forms the electronic invoice consumer consumption behavior data clusters model.
- 9. according to the method described in claim 3, it is characterized in that, the indicator vector of the example to be sorted and the cluster mould The method that feature vector in type is compared includes：In the indicator vector and the Clustering Model that calculate the example to be sorted All feature vectors distance, wherein apart from reckling be and the immediate described eigenvector V of example to be sorted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057864.5A CN108268898A (en) | 2018-01-19 | 2018-01-19 | A kind of electronic invoice user clustering method based on K-Means |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057864.5A CN108268898A (en) | 2018-01-19 | 2018-01-19 | A kind of electronic invoice user clustering method based on K-Means |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108268898A true CN108268898A (en) | 2018-07-10 |
Family
ID=62776207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810057864.5A Pending CN108268898A (en) | 2018-01-19 | 2018-01-19 | A kind of electronic invoice user clustering method based on K-Means |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108268898A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299259A (en) * | 2018-09-26 | 2019-02-01 | 深圳壹账通智能科技有限公司 | Enterprise's invoice data monitoring method, device, computer equipment and storage medium |
| CN111191713A (en) * | 2019-12-27 | 2020-05-22 | 大象慧云信息技术有限公司 | User portrait method and device based on invoice data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020135474A1 (en) * | 2001-03-21 | 2002-09-26 | Sylliassen Douglas G. | Method and device for sensor-based power management of a consumer electronic device |
| CN104899602A (en) * | 2015-06-03 | 2015-09-09 | 江苏马上游科技股份有限公司 | User cluster analysis system based on K-means algorithm |
| CN105844302A (en) * | 2016-04-07 | 2016-08-10 | 南京新与力文化传播有限公司 | Depth-learning-based method for automatically calculating commodity trend indexes |
| CN105931068A (en) * | 2015-12-30 | 2016-09-07 | 中国银联股份有限公司 | Cardholder consumption figure generation method and device |
| CN106021376A (en) * | 2016-05-11 | 2016-10-12 | 上海点荣金融信息服务有限责任公司 | Method and device for processing user information |
| CN106127493A (en) * | 2016-06-23 | 2016-11-16 | 深圳大学 | A kind of method and device analyzing customer transaction behavior |
| CN106548255A (en) * | 2016-11-24 | 2017-03-29 | 山东浪潮云服务信息科技有限公司 | A kind of Method of Commodity Recommendation based on mass users behavior |
| CN107220856A (en) * | 2017-06-02 | 2017-09-29 | 武汉大学 | A kind of system and method for mobile consumption group identification |
| CN206610379U (en) * | 2017-03-06 | 2017-11-03 | 中国—东盟信息港股份有限公司 | A kind of ecommerce shopping guide purchasing article |
-
2018
- 2018-01-19 CN CN201810057864.5A patent/CN108268898A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020135474A1 (en) * | 2001-03-21 | 2002-09-26 | Sylliassen Douglas G. | Method and device for sensor-based power management of a consumer electronic device |
| CN104899602A (en) * | 2015-06-03 | 2015-09-09 | 江苏马上游科技股份有限公司 | User cluster analysis system based on K-means algorithm |
| CN105931068A (en) * | 2015-12-30 | 2016-09-07 | 中国银联股份有限公司 | Cardholder consumption figure generation method and device |
| CN105844302A (en) * | 2016-04-07 | 2016-08-10 | 南京新与力文化传播有限公司 | Depth-learning-based method for automatically calculating commodity trend indexes |
| CN106021376A (en) * | 2016-05-11 | 2016-10-12 | 上海点荣金融信息服务有限责任公司 | Method and device for processing user information |
| CN106127493A (en) * | 2016-06-23 | 2016-11-16 | 深圳大学 | A kind of method and device analyzing customer transaction behavior |
| CN106548255A (en) * | 2016-11-24 | 2017-03-29 | 山东浪潮云服务信息科技有限公司 | A kind of Method of Commodity Recommendation based on mass users behavior |
| CN206610379U (en) * | 2017-03-06 | 2017-11-03 | 中国—东盟信息港股份有限公司 | A kind of ecommerce shopping guide purchasing article |
| CN107220856A (en) * | 2017-06-02 | 2017-09-29 | 武汉大学 | A kind of system and method for mobile consumption group identification |
Non-Patent Citations (1)
| Title |
|---|
| 宋军: "基于大数据分析的客户维系支撑系统建设和应用", 《现代电信科技》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299259A (en) * | 2018-09-26 | 2019-02-01 | 深圳壹账通智能科技有限公司 | Enterprise's invoice data monitoring method, device, computer equipment and storage medium |
| WO2020062702A1 (en) * | 2018-09-26 | 2020-04-02 | 深圳壹账通智能科技有限公司 | Method and device for sending text messages, computer device and storage medium |
| CN111191713A (en) * | 2019-12-27 | 2020-05-22 | 大象慧云信息技术有限公司 | User portrait method and device based on invoice data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108733798B (en) | Knowledge graph-based personalized recommendation method | |
| Bai et al. | Integrating Fuzzy C-Means and TOPSIS for performance evaluation: An application and comparative analysis | |
| CN106529968A (en) | Customer classification method and system thereof based on transaction data | |
| CN110956273A (en) | Credit scoring method and system integrating multiple machine learning models | |
| CN107066616A (en) | Method, device and electronic equipment for account processing | |
| CN105225135B (en) | Potential customer identification method and device | |
| CN108090800A (en) | A kind of game item method for pushing and device based on player's consumption potentiality | |
| CN105389713A (en) | Mobile data traffic package recommendation algorithm based on user historical data | |
| CN108898476A (en) | A kind of loan customer credit-graded approach and device | |
| CN112232930A (en) | E-commerce platform customer segmentation method based on weighted RFM model | |
| CN111967971A (en) | Bank client data processing method and device | |
| CN110532429B (en) | Online user group classification method and device based on clustering and association rules | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN107633035A (en) | A kind of shared transport services reorder predictor methods based on K Means＆LightGBM models | |
| CN105956122A (en) | Object attribute determining method and device | |
| CN107274066A (en) | A kind of shared traffic Customer Value Analysis method based on LRFMD models | |
| CN116187808A (en) | Electric power package recommendation method based on virtual power plant user-package label portrait | |
| CN108268898A (en) | A kind of electronic invoice user clustering method based on K-Means | |
| CN109583712B (en) | Data index analysis method and device and storage medium | |
| Yang et al. | Whales, dolphins, or minnows? towards the player clustering in free online games based on purchasing behavior via data mining technique | |
| CN111984842B (en) | Bank customer data processing method and device | |
| CN111967973B (en) | Bank customer data processing method and device | |
| CN110941771B (en) | Commodity parallel dynamic pushing method in e-commerce platform | |
| CN110309424A (en) | A kind of socialization recommended method based on Rough clustering | |
| Chen et al. | A divide-and-conquer-based approach for diverse group stock portfolio optimization using island-based genetic algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180710 |
|
| WD01 | Invention patent application deemed withdrawn after publication |